Merge branch 'ppc-for-upstream' of git://repo.or.cz/qemu/agraf

* 'ppc-for-upstream' of git://repo.or.cz/qemu/agraf: (35 commits)
  PPC: KVM: Fix BAT put
  PPC: e500: Only expose even TLB sizes in initial TLB
  ppc/pseries: Reset VPA registration on CPU reset
  pseries: Don't test for MSR_PR for hypercalls under KVM
  PPC: e500: calculate initrd_base like dt_base
  PPC: e500: increase DTC_LOAD_PAD
  device tree: simplify dumpdtb code
  fdt: move dumpdtb interpretation code to device_tree.c
  target-ppc: Remove unused power_mode field from cpu state
  pseries: Set hash table size based on RAM size
  pseries: Remove unnecessary locking from PAPR hash table hcalls
  ppc405_uc: Fix buffer overflow
  target-ppc: KVM: Fix some kernel version edge cases for kvmppc_reset_htab()
  pseries: Fix semantics of RTAS int-on, int-off and set-xive functions
  pseries: Rework implementation of TCE bypass
  pseries: Remove never used flags field from spapr vio devices
  pseries: Remove XICS irq type enum type
  pseries: Remove C bitfields from xics code
  pseries: Small cleanup to H_CEDE implementation
  pseries: Fix XICS reset
  ...

6 files changed, 152 insertions, 146 deletions

diff --git a/target-ppc/cpu.h b/target-ppc/cpu.h
index ca2fc2198e..faf4404078 100644
--- a/target-ppc/cpu.h
+++ b/target-ppc/cpu.h
@@ -1079,7 +1079,6 @@ struct CPUPPCState {
     int mmu_idx;         /* precomputed MMU index to speed up mem accesses */
 
     /* Power management */
-    int power_mode;
     int (*check_pow)(CPUPPCState *env);
 
 #if !defined(CONFIG_USER_ONLY)
diff --git a/target-ppc/int_helper.c b/target-ppc/int_helper.c
index f638b2a07c..f39b4f682a 100644
--- a/target-ppc/int_helper.c
+++ b/target-ppc/int_helper.c
@@ -287,23 +287,6 @@ target_ulong helper_602_mfrom(target_ulong arg)
     for (index = ARRAY_SIZE(r->element)-1; index >= 0; index--)
 #endif
 
-/* If X is a NaN, store the corresponding QNaN into RESULT.  Otherwise,
- * execute the following block.  */
-#define DO_HANDLE_NAN(result, x)                        \
-    if (float32_is_any_nan(x)) {                        \
-        CPU_FloatU __f;                                 \
-        __f.f = x;                                      \
-        __f.l = __f.l | (1 << 22);  /* Set QNaN bit. */ \
-        result = __f.f;                                 \
-    } else
-
-#define HANDLE_NAN1(result, x)                  \
-    DO_HANDLE_NAN(result, x)
-#define HANDLE_NAN2(result, x, y)                       \
-    DO_HANDLE_NAN(result, x) DO_HANDLE_NAN(result, y)
-#define HANDLE_NAN3(result, x, y, z)                                    \
-    DO_HANDLE_NAN(result, x) DO_HANDLE_NAN(result, y) DO_HANDLE_NAN(result, z)
-
 /* Saturating arithmetic helpers.  */
 #define SATCVT(from, to, from_type, to_type, min, max)          \
     static inline to_type cvt##from##to(from_type x, int *sat)  \
@@ -409,15 +392,29 @@ VARITH(uwm, u32)
         int i;                                                          \
                                                                         \
         for (i = 0; i < ARRAY_SIZE(r->f); i++) {                        \
-            HANDLE_NAN2(r->f[i], a->f[i], b->f[i]) {                    \
-                r->f[i] = func(a->f[i], b->f[i], &env->vec_status);     \
-            }                                                           \
+            r->f[i] = func(a->f[i], b->f[i], &env->vec_status);         \
         }                                                               \
     }
 VARITHFP(addfp, float32_add)
 VARITHFP(subfp, float32_sub)
+VARITHFP(minfp, float32_min)
+VARITHFP(maxfp, float32_max)
 #undef VARITHFP
 
+#define VARITHFPFMA(suffix, type)                                       \
+    void helper_v##suffix(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *a, \
+                           ppc_avr_t *b, ppc_avr_t *c)                  \
+    {                                                                   \
+        int i;                                                          \
+        for (i = 0; i < ARRAY_SIZE(r->f); i++) {                        \
+            r->f[i] = float32_muladd(a->f[i], c->f[i], b->f[i],         \
+                                     type, &env->vec_status);           \
+        }                                                               \
+    }
+VARITHFPFMA(maddfp, 0);
+VARITHFPFMA(nmsubfp, float_muladd_negate_result | float_muladd_negate_c);
+#undef VARITHFPFMA
+
 #define VARITHSAT_CASE(type, op, cvt, element)                          \
     {                                                                   \
         type result = (type)a->element[i] op (type)b->element[i];       \
@@ -649,27 +646,6 @@ VCT(uxs, cvtsduw, u32)
 VCT(sxs, cvtsdsw, s32)
 #undef VCT
 
-void helper_vmaddfp(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b,
-                    ppc_avr_t *c)
-{
-    int i;
-
-    for (i = 0; i < ARRAY_SIZE(r->f); i++) {
-        HANDLE_NAN3(r->f[i], a->f[i], b->f[i], c->f[i]) {
-            /* Need to do the computation in higher precision and round
-             * once at the end.  */
-            float64 af, bf, cf, t;
-
-            af = float32_to_float64(a->f[i], &env->vec_status);
-            bf = float32_to_float64(b->f[i], &env->vec_status);
-            cf = float32_to_float64(c->f[i], &env->vec_status);
-            t = float64_mul(af, cf, &env->vec_status);
-            t = float64_add(t, bf, &env->vec_status);
-            r->f[i] = float64_to_float32(t, &env->vec_status);
-        }
-    }
-}
-
 void helper_vmhaddshs(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *a,
                       ppc_avr_t *b, ppc_avr_t *c)
 {
@@ -730,27 +706,6 @@ VMINMAX(uw, u32)
 #undef VMINMAX_DO
 #undef VMINMAX
 
-#define VMINMAXFP(suffix, rT, rF)                                       \
-    void helper_v##suffix(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *a, \
-                          ppc_avr_t *b)                                 \
-    {                                                                   \
-        int i;                                                          \
-                                                                        \
-        for (i = 0; i < ARRAY_SIZE(r->f); i++) {                        \
-            HANDLE_NAN2(r->f[i], a->f[i], b->f[i]) {                    \
-                if (float32_lt_quiet(a->f[i], b->f[i],                  \
-                                     &env->vec_status)) {               \
-                    r->f[i] = rT->f[i];                                 \
-                } else {                                                \
-                    r->f[i] = rF->f[i];                                 \
-                }                                                       \
-            }                                                           \
-        }                                                               \
-    }
-VMINMAXFP(minfp, a, b)
-VMINMAXFP(maxfp, b, a)
-#undef VMINMAXFP
-
 void helper_vmladduhm(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, ppc_avr_t *c)
 {
     int i;
@@ -930,28 +885,6 @@ VMUL(uh, u16, u32)
 #undef VMUL_DO
 #undef VMUL
 
-void helper_vnmsubfp(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *a,
-                     ppc_avr_t *b, ppc_avr_t *c)
-{
-    int i;
-
-    for (i = 0; i < ARRAY_SIZE(r->f); i++) {
-        HANDLE_NAN3(r->f[i], a->f[i], b->f[i], c->f[i]) {
-            /* Need to do the computation is higher precision and round
-             * once at the end.  */
-            float64 af, bf, cf, t;
-
-            af = float32_to_float64(a->f[i], &env->vec_status);
-            bf = float32_to_float64(b->f[i], &env->vec_status);
-            cf = float32_to_float64(c->f[i], &env->vec_status);
-            t = float64_mul(af, cf, &env->vec_status);
-            t = float64_sub(t, bf, &env->vec_status);
-            t = float64_chs(t);
-            r->f[i] = float64_to_float32(t, &env->vec_status);
-        }
-    }
-}
-
 void helper_vperm(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b,
                   ppc_avr_t *c)
 {
@@ -1039,9 +972,7 @@ void helper_vrefp(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *b)
     int i;
 
     for (i = 0; i < ARRAY_SIZE(r->f); i++) {
-        HANDLE_NAN1(r->f[i], b->f[i]) {
-            r->f[i] = float32_div(float32_one, b->f[i], &env->vec_status);
-        }
+        r->f[i] = float32_div(float32_one, b->f[i], &env->vec_status);
     }
 }
 
@@ -1054,9 +985,7 @@ void helper_vrefp(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *b)
                                                                 \
         set_float_rounding_mode(rounding, &s);                  \
         for (i = 0; i < ARRAY_SIZE(r->f); i++) {                \
-            HANDLE_NAN1(r->f[i], b->f[i]) {                     \
-                r->f[i] = float32_round_to_int (b->f[i], &s);   \
-            }                                                   \
+            r->f[i] = float32_round_to_int (b->f[i], &s);       \
         }                                                       \
     }
 VRFI(n, float_round_nearest_even)
@@ -1089,11 +1018,9 @@ void helper_vrsqrtefp(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *b)
     int i;
 
     for (i = 0; i < ARRAY_SIZE(r->f); i++) {
-        HANDLE_NAN1(r->f[i], b->f[i]) {
-            float32 t = float32_sqrt(b->f[i], &env->vec_status);
+        float32 t = float32_sqrt(b->f[i], &env->vec_status);
 
-            r->f[i] = float32_div(float32_one, t, &env->vec_status);
-        }
+        r->f[i] = float32_div(float32_one, t, &env->vec_status);
     }
 }
 
@@ -1109,9 +1036,7 @@ void helper_vexptefp(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *b)
     int i;
 
     for (i = 0; i < ARRAY_SIZE(r->f); i++) {
-        HANDLE_NAN1(r->f[i], b->f[i]) {
-            r->f[i] = float32_exp2(b->f[i], &env->vec_status);
-        }
+        r->f[i] = float32_exp2(b->f[i], &env->vec_status);
     }
 }
 
@@ -1120,9 +1045,7 @@ void helper_vlogefp(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *b)
     int i;
 
     for (i = 0; i < ARRAY_SIZE(r->f); i++) {
-        HANDLE_NAN1(r->f[i], b->f[i]) {
-            r->f[i] = float32_log2(b->f[i], &env->vec_status);
-        }
+        r->f[i] = float32_log2(b->f[i], &env->vec_status);
     }
 }
 
@@ -1473,10 +1396,6 @@ VUPK(lsh, s32, s16, UPKLO)
 #undef UPKHI
 #undef UPKLO
 
-#undef DO_HANDLE_NAN
-#undef HANDLE_NAN1
-#undef HANDLE_NAN2
-#undef HANDLE_NAN3
 #undef VECTOR_FOR_INORDER_I
 #undef HI_IDX
 #undef LO_IDX
diff --git a/target-ppc/kvm.c b/target-ppc/kvm.c
index 7f6e4e0b87..5cbe98a164 100644
--- a/target-ppc/kvm.c
+++ b/target-ppc/kvm.c
@@ -60,6 +60,7 @@ static int cap_booke_sregs;
 static int cap_ppc_smt;
 static int cap_ppc_rma;
 static int cap_spapr_tce;
+static int cap_hior;
 
 /* XXX We have a race condition where we actually have a level triggered
  *     interrupt, but the infrastructure can't expose that yet, so the guest
@@ -86,6 +87,7 @@ int kvm_arch_init(KVMState *s)
     cap_ppc_smt = kvm_check_extension(s, KVM_CAP_PPC_SMT);
     cap_ppc_rma = kvm_check_extension(s, KVM_CAP_PPC_RMA);
     cap_spapr_tce = kvm_check_extension(s, KVM_CAP_SPAPR_TCE);
+    cap_hior = kvm_check_extension(s, KVM_CAP_PPC_HIOR);
 
     if (!cap_interrupt_level) {
         fprintf(stderr, "KVM: Couldn't find level irq capability. Expect the "
@@ -469,6 +471,54 @@ int kvm_arch_put_registers(CPUPPCState *env, int level)
         env->tlb_dirty = false;
     }
 
+    if (cap_segstate && (level >= KVM_PUT_RESET_STATE)) {
+        struct kvm_sregs sregs;
+
+        sregs.pvr = env->spr[SPR_PVR];
+
+        sregs.u.s.sdr1 = env->spr[SPR_SDR1];
+
+        /* Sync SLB */
+#ifdef TARGET_PPC64
+        for (i = 0; i < 64; i++) {
+            sregs.u.s.ppc64.slb[i].slbe = env->slb[i].esid;
+            sregs.u.s.ppc64.slb[i].slbv = env->slb[i].vsid;
+        }
+#endif
+
+        /* Sync SRs */
+        for (i = 0; i < 16; i++) {
+            sregs.u.s.ppc32.sr[i] = env->sr[i];
+        }
+
+        /* Sync BATs */
+        for (i = 0; i < 8; i++) {
+            /* Beware. We have to swap upper and lower bits here */
+            sregs.u.s.ppc32.dbat[i] = ((uint64_t)env->DBAT[0][i] << 32)
+                | env->DBAT[1][i];
+            sregs.u.s.ppc32.ibat[i] = ((uint64_t)env->IBAT[0][i] << 32)
+                | env->IBAT[1][i];
+        }
+
+        ret = kvm_vcpu_ioctl(env, KVM_SET_SREGS, &sregs);
+        if (ret) {
+            return ret;
+        }
+    }
+
+    if (cap_hior && (level >= KVM_PUT_RESET_STATE)) {
+        uint64_t hior = env->spr[SPR_HIOR];
+        struct kvm_one_reg reg = {
+            .id = KVM_REG_PPC_HIOR,
+            .addr = (uintptr_t) &hior,
+        };
+
+        ret = kvm_vcpu_ioctl(env, KVM_SET_ONE_REG, &reg);
+        if (ret) {
+            return ret;
+        }
+    }
+
     return ret;
 }
 
@@ -946,52 +996,14 @@ int kvmppc_get_hypercall(CPUPPCState *env, uint8_t *buf, int buf_len)
 void kvmppc_set_papr(CPUPPCState *env)
 {
     struct kvm_enable_cap cap = {};
-    struct kvm_one_reg reg = {};
-    struct kvm_sregs sregs = {};
     int ret;
-    uint64_t hior = env->spr[SPR_HIOR];
 
     cap.cap = KVM_CAP_PPC_PAPR;
     ret = kvm_vcpu_ioctl(env, KVM_ENABLE_CAP, &cap);
 
     if (ret) {
-        goto fail;
-    }
-
-    /*
-     * XXX We set HIOR here. It really should be a qdev property of
-     *     the CPU node, but we don't have CPUs converted to qdev yet.
-     *
-     *     Once we have qdev CPUs, move HIOR to a qdev property and
-     *     remove this chunk.
-     */
-    reg.id = KVM_REG_PPC_HIOR;
-    reg.addr = (uintptr_t)&hior;
-    ret = kvm_vcpu_ioctl(env, KVM_SET_ONE_REG, &reg);
-    if (ret) {
-        fprintf(stderr, "Couldn't set HIOR. Maybe you're running an old \n"
-                        "kernel with support for HV KVM but no PAPR PR \n"
-                        "KVM in which case things will work. If they don't \n"
-                        "please update your host kernel!\n");
-    }
-
-    /* Set SDR1 so kernel space finds the HTAB */
-    ret = kvm_vcpu_ioctl(env, KVM_GET_SREGS, &sregs);
-    if (ret) {
-        goto fail;
+        cpu_abort(env, "This KVM version does not support PAPR\n");
     }
-
-    sregs.u.s.sdr1 = env->spr[SPR_SDR1];
-
-    ret = kvm_vcpu_ioctl(env, KVM_SET_SREGS, &sregs);
-    if (ret) {
-        goto fail;
-    }
-
-    return;
-
-fail:
-    cpu_abort(env, "This KVM version does not support PAPR\n");
 }
 
 int kvmppc_smt_threads(void)
@@ -999,6 +1011,7 @@ int kvmppc_smt_threads(void)
     return cap_ppc_smt ? cap_ppc_smt : 1;
 }
 
+#ifdef TARGET_PPC64
 off_t kvmppc_alloc_rma(const char *name, MemoryRegion *sysmem)
 {
     void *rma;
@@ -1042,6 +1055,16 @@ off_t kvmppc_alloc_rma(const char *name, MemoryRegion *sysmem)
     return size;
 }
 
+uint64_t kvmppc_rma_size(uint64_t current_size, unsigned int hash_shift)
+{
+    if (cap_ppc_rma >= 2) {
+        return current_size;
+    }
+    return MIN(current_size,
+               getrampagesize() << (hash_shift - 7));
+}
+#endif
+
 void *kvmppc_create_spapr_tce(uint32_t liobn, uint32_t window_size, int *pfd)
 {
     struct kvm_create_spapr_tce args = {
@@ -1101,6 +1124,44 @@ int kvmppc_remove_spapr_tce(void *table, int fd, uint32_t window_size)
     return 0;
 }
 
+int kvmppc_reset_htab(int shift_hint)
+{
+    uint32_t shift = shift_hint;
+
+    if (!kvm_enabled()) {
+        /* Full emulation, tell caller to allocate htab itself */
+        return 0;
+    }
+    if (kvm_check_extension(kvm_state, KVM_CAP_PPC_ALLOC_HTAB)) {
+        int ret;
+        ret = kvm_vm_ioctl(kvm_state, KVM_PPC_ALLOCATE_HTAB, &shift);
+        if (ret == -ENOTTY) {
+            /* At least some versions of PR KVM advertise the
+             * capability, but don't implement the ioctl().  Oops.
+             * Return 0 so that we allocate the htab in qemu, as is
+             * correct for PR. */
+            return 0;
+        } else if (ret < 0) {
+            return ret;
+        }
+        return shift;
+    }
+
+    /* We have a kernel that predates the htab reset calls.  For PR
+     * KVM, we need to allocate the htab ourselves, for an HV KVM of
+     * this era, it has allocated a 16MB fixed size hash table
+     * already.  Kernels of this era have the GET_PVINFO capability
+     * only on PR, so we use this hack to determine the right
+     * answer */
+    if (kvm_check_extension(kvm_state, KVM_CAP_PPC_GET_PVINFO)) {
+        /* PR - tell caller to allocate htab */
+        return 0;
+    } else {
+        /* HV - assume 16MB kernel allocated htab */
+        return 24;
+    }
+}
+
 static inline uint32_t mfpvr(void)
 {
     uint32_t pvr;
diff --git a/target-ppc/kvm_ppc.h b/target-ppc/kvm_ppc.h
index e2f8703853..baad6eb75b 100644
--- a/target-ppc/kvm_ppc.h
+++ b/target-ppc/kvm_ppc.h
@@ -27,6 +27,8 @@ int kvmppc_smt_threads(void);
 off_t kvmppc_alloc_rma(const char *name, MemoryRegion *sysmem);
 void *kvmppc_create_spapr_tce(uint32_t liobn, uint32_t window_size, int *pfd);
 int kvmppc_remove_spapr_tce(void *table, int pfd, uint32_t window_size);
+int kvmppc_reset_htab(int shift_hint);
+uint64_t kvmppc_rma_size(uint64_t current_size, unsigned int hash_shift);
 #endif /* !CONFIG_USER_ONLY */
 const ppc_def_t *kvmppc_host_cpu_def(void);
 int kvmppc_fixup_cpu(CPUPPCState *env);
@@ -94,6 +96,23 @@ static inline int kvmppc_remove_spapr_tce(void *table, int pfd,
 {
     return -1;
 }
+
+static inline int kvmppc_reset_htab(int shift_hint)
+{
+    return -1;
+}
+
+static inline uint64_t kvmppc_rma_size(uint64_t current_size,
+                                       unsigned int hash_shift)
+{
+    return ram_size;
+}
+
+static inline int kvmppc_update_sdr1(CPUPPCState *env)
+{
+    return 0;
+}
+
 #endif /* !CONFIG_USER_ONLY */
 
 static inline const ppc_def_t *kvmppc_host_cpu_def(void)
diff --git a/target-ppc/machine.c b/target-ppc/machine.c
index d6c2ee41b3..21ce7575e3 100644
--- a/target-ppc/machine.c
+++ b/target-ppc/machine.c
@@ -82,7 +82,7 @@ void cpu_save(QEMUFile *f, void *opaque)
     qemu_put_betls(f, &env->hflags);
     qemu_put_betls(f, &env->hflags_nmsr);
     qemu_put_sbe32s(f, &env->mmu_idx);
-    qemu_put_sbe32s(f, &env->power_mode);
+    qemu_put_sbe32(f, 0);
 }
 
 int cpu_load(QEMUFile *f, void *opaque, int version_id)
@@ -167,7 +167,7 @@ int cpu_load(QEMUFile *f, void *opaque, int version_id)
     qemu_get_betls(f, &env->hflags);
     qemu_get_betls(f, &env->hflags_nmsr);
     qemu_get_sbe32s(f, &env->mmu_idx);
-    qemu_get_sbe32s(f, &env->power_mode);
+    qemu_get_sbe32(f); /* Discard unused power_mode */
 
     return 0;
 }
diff --git a/target-ppc/translate_init.c b/target-ppc/translate_init.c
index fba2b42427..a972287035 100644
--- a/target-ppc/translate_init.c
+++ b/target-ppc/translate_init.c
@@ -10423,6 +10423,14 @@ static void ppc_cpu_reset(CPUState *s)
     env->pending_interrupts = 0;
     env->exception_index = POWERPC_EXCP_NONE;
     env->error_code = 0;
+
+#if defined(TARGET_PPC64) && !defined(CONFIG_USER_ONLY)
+    env->vpa = 0;
+    env->slb_shadow = 0;
+    env->dispatch_trace_log = 0;
+    env->dtl_size = 0;
+#endif /* TARGET_PPC64 */
+
     /* Flush all TLBs */
     tlb_flush(env, 1);
 }